Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3242 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.8288. Min Act: -0.1700
Data Index: 587548 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7975. Min Act: -0.1700
Data Index: 2650977 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7663. Min Act: -0.1700
Data Index: 1259220 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7038. Min Act: -0.1700
Data Index: 6902504 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7038. Min Act: -0.1700
Data Index: 2019750 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7038. Min Act: -0.1700
Data Index: 2844627 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6725. Min Act: -0.1700
Data Index: 4027790 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6413. Min Act: -0.1700
Data Index: 2038406 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6413. Min Act: -0.1700
Data Index: 2019751 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6413. Min Act: -0.1700
Data Index: 6091948 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6100. Min Act: -0.1700
Data Index: 7955196 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6100. Min Act: -0.1700
Data Index: 6056877 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6100. Min Act: -0.1700
Data Index: 4277221 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6100. Min Act: -0.1700
Data Index: 1460777 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6100. Min Act: -0.1700
Data Index: 5518189 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6100. Min Act: -0.1700
Data Index: 1259203 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6100. Min Act: -0.1700
Data Index: 7472030 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6100. Min Act: -0.1700
Data Index: 792589 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.5788. Min Act: -0.1700
Data Index: 6419403 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.5788. Min Act: -0.1700
Data Index: 4277222 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19